Dataset for the Article: nablaColors: A 3D Benchmark for Optical Property Prediction with Solvent-aware Graph Neural Networks
Bibliographic record
Abstract
This dataset provides curated molecular conformations and predefined splits for benchmarking machine learning models in optical absorption prediction. The core file, absorption_conformations.zip, contains an LMDB database of molecular geometries optimized at multiple levels of theory (xTB, DFT in vacuum, and DFT with implicit solvent). The accompanying CSV files (absorption_pairs_all.csv, absorption_train.csv, absorption_val.csv, absorption_test.csv) define the train/validation/test splits for supervised absorption prediction. To support robust evaluation, scaffold-based cross-validation splits are also provided for both single-property absorption (absorption_crossval.zip) and multitarget learning (multitarget_crossval.zip). The files smiles_to_replace.csv and smiles_to_remove.csv document corrections and exclusions applied during curation to ensure dataset quality. Together, these resources enable reproducible training and evaluation of 2D and 3D models for molecular optical property prediction. Examples of how to read from the LMDB databases are available at: https://github.com/AI4DD/nablaColors. This dataset compiles experimental data on absorption and emission maxima, as well as photoluminescence quantum yield, from the following sources: Joung et al. (2020), Ju et al. (2021), Venkatraman et al. (2018), and Venkatraman & Chellappan (2020).In addition to the dataset and splits, this release includes four pretrained UniProp checkpoints trained on the provided conformations. Examples of validation and inference available at: https://github.com/AI4DD/nablaColors.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.003 | 0.001 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.001 |
| Science and technology studies | 0.003 | 0.001 |
| Scholarly communication | 0.003 | 0.000 |
| Open science | 0.002 | 0.002 |
| Research integrity | 0.000 | 0.001 |
| Insufficient payload (model declined to judge) | 0.007 | 0.002 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; both teacher heads agree on what is shown here.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".